United States

Using a table-top roleplaying game, researchers work to identify the ways in which a socially assistive robot should both look, as well as what capabilities it should have for the individual user. Focusing on major depressive disorder, the game takes participants through the day in the life of someone living with depression, and seeks to identify ways in which this personalized robot might aid participants facing depression symptoms.

IEEE RO-MAN 2021

Tradeoff-Focused Contrastive Explanation for MDP Planning

tabletop roleplaying game

human robot interaction

design

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. This theme also touches upon people's expectations and perceptions of robots, as well as other social, cognitive and cultural factors that will influence human-robot interactions. We will have a special session/track on this topic, invite targeted submissions and include plenary speakers who are specialist in this area. We sincerely hope that this focus will help enlighten the design-thinking of all of us as we fabricate and program our own various systems.

To access RO-MAN Virtual 2021, [please register here.](https://ro-man2021.org/registration/)

RO-MAN 2021's theme is trustworthiness and cooperation. We chose this term well before the pandemic put the world on edge and added a new reason for us to question our own personal safety when in the company of others. But what about in the company of social robots? What would cause us to trust, or not trust, them? How do we as researchers create that feeling, that critical component of any relationship? With social robots, it is of course largely in our power to design the physical form, the control code and the interface software to maximize trustworthiness, facilitate cooperation and enhance the quality of human-robot interaction. 

panel

Like most machines, robots may sometimes behave in an erroneous manner. Nevertheless, when a robot has been taught a task by humans, we test if the teachers ignore small mistakes made by the robot if it shows significant improvements while practising the task. We first conducted a study in which the perceived severity of different robot errors in a household chore was investigated. We then used the results to create teaching scenarios of different levels of error severity and conducted a second study. Even small errors significantly affected trust and big errors had a more adverse impact.

Context Dependent Trajectory Generation using Sequence-to-Sequence Models for Robotic Toilet Cleaning

We developed POP Cart which is a shopping cart type agent system and recommend products. The system chats with the user to create a good relationship while shopping for recommendations. To evaluate the system, we conducted an experiment with 49 people in a supermarket. The results of the experiment showed that POP cart recommendations were more acceptable to users than simple recommendations and no recommendations.

POP Cart: Product Recommendation System by an Agent on a Shopping Cart

the goal of this study is to investigate the feasibility of integrating wearable sensors and machine learning techniques to detect in real-time the occurrence of challenging behaviours during child-robot interaction.
Our contributions are as follow:
1) Defining an effective annotation to distinguish challenge-
ing behaviours.
2) Investigating the influence of different physiological
signals in the prediction of challenging behaviours.
3) Development of an assistive annotation tool to monitor
the physiological signs, and to visualize the predictions of the developed machine learning algorithms.

Effect of Robot Agents on Teaching against Pseudoscience

In this work, we propose using information about the users’ disabilities and impairments to create a navigation prioritization layer for solving multi-robot navigation situations. To deal with the deep subjectivity inherent to assigning these priorities, we propose using human computation to create a navigation solution that will be aligned with humans’ personal value systems, increasing the perceived fairness and trustworthiness of the system.

Use of Human Computation for Coordinating Robotic Mobility Aids Based on User Impairments

Speaking and appearance modalities might give characters to the AI agent. We designed a 2(speech types: assistant-like vs. companion-like) × 2(flexibility types: flexible vs. hard) × 2(roughness types: rough vs. smooth) mixed-participant experiment to explore the users’ perception of the AI agent on usefulness, sociability, and service evaluation. The results showed that the texture affected the users’ perception of the AI agent and the users’ preference for a specific texture according to the speech type. Based on the results, we discussed the appropriate texture setting and speech type in specific context.

Effect of AI Agent's Speech and Tactility Types on Users' Perception

We proposed that the empathic ability of a social robot can be improved if the social robot can create facial expressions based on the emotional state of a user. Moreover, we suggested a framework of facial expressions for robots. These facial expressions can be repeatedly used in various social robot platforms to achieve such a strategy.

Robot Facial Expression Framework for Enhancing Empathy in Human-Robot Interaction

Imbuing furniture with robot properties reduces the physical labor and time needed for arranging spaces, such as homes, classrooms, and offices. Outsourcing labor tasks to robot furniture requires users' involvement with functional user interfaces. We performed a user study on multi-robot furniture and added additional features based on the study results. The study involved 12 participants rearranging multiple non-robotic and robotic chairs (ChairBots). Results from the video and interview analysis revealed five high-level features missing in the original ChairBot: dual screen-based user interface, the ability to save and to set arrangements, the ability to move in multi-robot formations, the ability to snap to angles/gridlines, and higher movement precision. The improved system allows users to control multiple furniture robots, both locally and remotely. Such improvement sets the baseline functionalities of robot furniture arrangement systems while extending the potential utilization of established robotic chairs.

Towards User-Centric Robot Furniture Arrangement

With the world population ageing the need to support independent living for older people is of paramount importance. This paper introduces a social robotic application to support healthy living at home as part of SHAPES project, how user requirements have been gathered directly with the end-users, to developing a social robot with chabot abilities that can offer videocalls, measure temperature and deliver reminders by approaching users. The robot will stay at older people’s homes and will promote real-world deployment of social robots.

Social Robotic Application to Support Active and Healthy Ageing

Recent research is emerging in the field of Social Robotics where robots have the potential to serve as tools to improve human well-being. However, research exploring the expectations and perceptions of prospective users of such robots, and the professionals who currently deliver these interventions, is limited. In this paper, we present qualitative analysis of discussions with prospective users and experienced coaches regarding the design of robot well-being coaches. We invited participants interested in well-being practices to take-part in a Participatory Design (PD) study, consisting of individual interviews and a focus group discussion (N_P = 8). Discussions focused on ideating how a robot could function as a mental well-being coach, based on their experiences with well-being practices. Data triangulation was employed by interviewing three professional coaches as additional sources of information. This resulted in a rich set of data, which we transcribed and analysed using Thematic Analysis (TA). The developed themes regarding robot features, form, behaviours, robot-led well-being practices, and the advantages and disadvantages these could provide, were compiled and are discussed in detail. We present this data together with tabulated quotes from the participants and coaches, to pave the way towards designing robot coaches that can provide supportive interventions to improve the mental health and well-being of their users.

When Positive Perception of the Robot Has No Effect On Learning

The goal of this research is to explore how collaborative robot (cobots) in factories could be used in ways that support pleasurable worker experiences using ”research through design” (RtD) method. We developed three scenarios which would evoke fellowship, inspiration, sense of safety and trust, and sens of superiority in human-robot collaboration. The scenarios were developed based on affectiveness, playfulness and relatedness and we evaluated them with 33 participants in two complementary workshops. Our novel interaction designs lead us to unveil participant's expectations towards cobot's behavior in the factory settings.

Acceptance of a minimal design of a human infant for facilitating affective interaction with older adults: A case study toward interactive doll therapy

Premium content

Tradeoff-Focused Contrastive Explanation for MDP Planning

Downloads

Next from IEEE RO-MAN 2021

Context Dependent Trajectory Generation using Sequence-to-Sequence Models for Robotic Toilet Cleaning

Similar lecture

Social norms and cooperation in a collective-risk social dilemma:comparing reinforcement learning and norm-based approaches